LLM Reasoning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

68 papers in the last four weeks, up 143% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 650

All topics

Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
Jun 26, 2026Tianlong Wang, Yuhang Wang, Weibin Liao +5Language Model Steering Representation Geometry in Language Models
National Engineering Research Center of Software Engineering, Peking University · School of Computer Science, Peking University · Key Laboratory of High Confidence Software Technologies, Ministry of Education +1
The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans
Jun 25, 2026Bella Fascendini, Kathryn McGregor, Max D. Gupta +1LLM Evaluation LLM Reasoning
Department of Psychology, Princeton University · Department of Computer Science, Princeton University
Einstein World Models
Jun 25, 2026Munachiso Samuel Nwadike, Zangir Iklassov, Ali Mekky +2LLM Tool Use Counterfactual Reasoning
MBZUAI · RIKEN AIP, Japan · Tohoku University
Reasoning Quality Emerges Early: Data Curation for Reasoning Models
Jun 25, 2026Hongyi Henry Jin, Wenhan Yang, Meysam Ghaffari +2LLM Fine-Tuning Training Data Selection
Department of Computer Science, University of California Los Angeles (UCLA), California, USA · Optum AI, UnitedHealth Group, Minneapolis, Minnesota, USA
Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation
Jun 25, 2026Han-yu WangComputational Cognitive Modeling Inference-Time Compute Allocation
The University of Hong Kong
Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law
Jun 24, 2026Tiansi Dong, Mateja Jamnik, Pietro LiòLogical Reasoning Symbolic Reasoning
The Alan Turing Institute, 96 Euston Road, London, NW1 2DB, UK. · Department of Computer Science and Technology, University of Cambridge, 15 JJ Thomson Ave., Cambridge, CB3 0FD, UK.
Learning with a Single Rollout via Monte Carlo Pass@k Critic
Jun 24, 2026Fengdi Che, Yang Liu, Lei Yu +4RL for Language Model Reasoning Credit Assignment in RL
University of Alberta · BIGAI · University of Toronto +4
CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigation
Jun 24, 2026Shaoxuan Li, Xiangyu Dong, Xiaoguang Ma +3UAV Navigation Vision-Language Navigation
Foshan Graduate School of Innovation, Northeastern University, Foshan 528311, China · College of Information Science and Engineering, Northeastern University, Shenyang 110819, China · Faculty of Robot Science and Engineering, Northeastern University, Shenyang 110819, China +3
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
Jun 24, 2026Yutong Yin, Mingyu Jin, Jin Pan +12RL for Language Model Reasoning Test-Time Scaling
1Northwestern University · 2Rutgers University · University of Wisconsin–Madison +7
ScaleToT: Generalizing Structured LLM Reasoning for Billion-Scale Low-Activity User Modeling
Jun 23, 2026Tianbao Ma, Chang Xi, Yichuan Zou +7User Modeling LLM Reasoning
Kuaishou Technology, Beijing, China
Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization
Jun 23, 2026Kanishk AwadhiyaLLM Inference Representation Geometry in Language Models
Independent Researcher
Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War
Jun 23, 2026Arnaud RicciStrategic Reasoning Risks in Language Models AI Agent Benchmarks
Independent researcher, Switzerland.
VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification
Jun 23, 2026Ninghan Zhong, Ahmet Ege Tanriverdi, Kaan Kale +1Formal Verification Structured Reasoning
School of Electrical and Computer Engineering, Georgia Institute of Technology, USA · Department of Electrical and Computer Engineering, Bogazici University, Turkey
Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning
Jun 23, 2026Tianyuan Shi, Canbin Huang, Bei Li +4RL for Language Model Reasoning Language Model Distillation
School of Computer Science and Engineering, Sun Yat-sen University, China · Meituan, Inc., China · Shenzhen Loop Area Institute, China +1
Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models
Jun 22, 2026Jiawei Xu, Minghui Liu, Aakriti Agrawal +2Masked Diffusion Models Language Model Decoding
University of Maryland, College Park · University of California, Los Angeles.
HOLMES: Evaluating Higher-Order Logical Reasoning in LLMs
Jun 22, 2026Yucheng Wu, Jundong Xu, Mingzhen Ju +4Logical Reasoning LLM Evaluation
State Key Laboratory of Multimedia Information Processing, Peking University · School of Computer Science, Peking University · School of Computing, National University of Singapore +3
ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation
Jun 22, 2026Chen Lin, Kedi Chen, Wei ZhangCoT Distillation Language Model Distillation
East China Normal University · Shanghai Innovation Institute
Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently
Jun 22, 2026Stanley Wei, Juno KimRL for Language Model Reasoning Efficient Language Model Reasoning
1Princeton University · University of California, Berkeley.
Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation
Jun 22, 2026Jinwei Xiao, Zhuowen Han, Yueqing Sun +6CoT Distillation On-Policy Distillation
Meituan Longcat Team · TJUNLP Lab, College of Intelligence and Computing, Tianjin University · Nanjing University
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Jun 20, 2026Xuanming Zhang, Sining Zhoubian, Yuxuan Chen +8LLM Alignment Language Model Decoding
Qwen Team, Alibaba Inc. · Tsinghua University · Nanyang Technological University
ForEx: A Formal Verification Framework for Explainable Reasoning in Logical Fallacy Detection and Annotation
Jun 20, 2026Pei-Cing Huang, Chienyu Liu, Chan Hsu +3Logical Reasoning Explainability Evaluation
Department of Information Management National Sun Yat-Sen University Kaohsiung, Taiwan · Graduate Institute of Data Science & Information Computing National Chung Hsing University Taichung, Taiwan
Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers
Jun 19, 2026Vatsal Ananthula, Adarsh KumarappanFaithfulness of Language Model Explanations LLM Auditing
University of California, Berkeley · 2California Institute of Technology
LLM and Human Modes of Representation
Jun 19, 2026Shalom LappinLLM Evaluation LLM Reasoning
Queen Mary University of London and King’s College London
Depth-Entropy Guided Sampling for Training-Free LLM Reasoning
Jun 19, 2026Zibin Meng, Peng Xie, Kani ChenLLM Inference Test-Time Scaling
1The Hong Kong University of Science and Technology
Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning
Jun 19, 2026Noor Islam S. Mohammad, Mahmudul HasanLLM Evaluation Reasoning Consistency in Language Models
Department of Computer Science, Informatics Institute, Istanbul Technical University, ˙Istanbul, Türkiye · School of Information Technology, Deakin University, Geelong, VIC 3220, Australia
QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation
Jun 18, 2026Xinyi Zheng, Ling Shi, Tianlong Yu +3Logical Reasoning LLM Evaluation
Huazhong University of Science and Technology Wuhan, China · Nanyang Technological University Singapore, Singapore · Hubei University Wuhan, China +2
CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs
Jun 18, 2026Chengwen Liu, Hao Peng, Jisheng Dang +3Reward Shaping Video Reasoning
School of Information Science and Engineering, Lanzhou University, Lanzhou, China · School of Medical Technology, Beijing Institute of Technology, Beijing, China · School of Computing, National University of Singapore, Singapore
CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models
Jun 18, 2026Yuxu Zhou, Ondřej Kuželka, Yuyi Wang +2LLM Evaluation LLM Reasoning
School of Artificial Intelligence, Jilin University, Changchun, China · Czech Technical University in Prague, Prague, Czech Republic · CRRC Zhuzhou Institute, Zhuzhou, China +3
Analyzing the Narration Gap in LLM-Solver Loops
Jun 17, 2026Zunchen Huang, Songgaojun DengAdversarial Attacks on LLMs Formal Verification
Centrum Wiskunde & Informatica, Amsterdam, The Netherlands · Eindhoven University of Technology, Eindhoven, The Netherlands
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Jun 17, 2026Zhilin Huang, Hang Gao, Ziqiang Dong +6LLM Self-Correction CoT Distillation
Qwen Business Unit of Alibaba · Tsinghua University · Peking University

Jun 26, 2026, cs.AIJ/K move · Enter open · S save

Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories

Tianlong Wang, Yuhang Wang, Weibin Liao, Xin Gao+4

National Engineering Research Center of Software Engineering, Peking University · School of Computer Science, Peking University · Key Laboratory of High Confidence Software Technologies, Ministry of Education+1

Language Model Steering Representation Geometry in Language Models LLM Reasoning

Open paper AskPDF arXiv

Current approaches to enhance Large Language Model (LLM) reasoning, such as Chain-of-Thought and "Wait" prompts, primarily encourage models to think more, yet often fail to guide them toward Truth. While Representation Editing (RepE) offers a intrinsic control, its application to dynamic reasoning trajectories remains underexplored. In this work, we bridge this gap by investigating the geometry of truth within unfolding reasoning chains. We uncover three critical insights: (1) Truth is encoded at the sentence level and is entangled with latent reasoning patterns; (2) Effective intervention follows an Uncertainty Principle and a Decay Effect, requiring localization to early, high-entropy forks; (3) Naive steering vectors suffer from noise, risking collateral damage to correct trajectories. Based on these findings, we propose DynaSteer, a dynamic RepE framework. DynaSteer employs pattern clustering to disentangle reasoning manifolds and utilizes Fisher-LDA to project purified truth. By dynamically monitoring lookahead entropy, it selectively steers and rolls back trajectories only when necessary. Comprehensive experimental results on several MATH benchmark verify the effectiveness of DynaSteer, and experiments on out-of-domain coding tasks further confirm its generalization ability. Our code is publicly available at https://github.com/tianlwang/DynaSteer.

Momentum

Related topics

Latest papers 650